© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40952
    Prev
    Next
    INDEX
    Explanations

    central banks, companies, planning, committees

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects mentions of banking institutions—especially the terms “central” and “bank” (e.g., “central bank” or “banks”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -2.00
     However
    -1.92
    uggets
    -1.88
    都沒有
    -1.82
    átiles
    -1.82
     glimpse
    -1.80
    Nuorodos
    -1.80
     Then
    -1.80
    hejiang
    -1.79
    犹如
    -1.76
    POSITIVE LOGITS
    ஂ
    2.23
    諼
    2.11
    褡
    2.02
    ｂ
    1.99
    0
    1.94
    ES
    1.85
    
    1.85
    c
    1.81
    at
    1.78
    t
    1.77
    Activations Density 0.003%

    No Known Activations